AMD Ryzen Z1 Extreme GPU vs Intel Arc Pro B370 Comparison

Head-to-Head Benchmarks

The recorded database contains no direct head-to-head benchmark entries for the AMD Ryzen Z1 Extreme GPU versus the Intel Arc Pro B370. Both parts register zero wins in the available comparison set, and neither has an average benchmark score or a list of nearest rivals. The absence of measured data means any direct performance comparison must be inferred from the architectural and specification record rather than from executed workloads.

What the specification data does show is a clear split in compute emphasis. The AMD Ryzen Z1 Extreme GPU delivers 8.294 TFLOPS of FP32 throughput, while the Intel Arc Pro B370 delivers 6.144 TFLOPS. That places the AMD part approximately 35% ahead in raw single-precision compute. In FP16, the AMD part reaches 16.59 TFLOPS (2:1) against 12.29 TFLOPS (2:1) for Intel, preserving the same proportional gap. The AMD part also leads in texture and pixel throughput: 129.6 GTexel/s versus 96.00 GTexel/s, and 86.40 GPixel/s versus 48.00 GPixel/s. The pixel rate advantage is substantial, roughly 80% higher, which points to a pronounced fill-rate advantage for AMD in rasterization-bound scenes.

The Intel part counters in shader count and ray tracing core count per watt. The Arc Pro B370 carries 1280 shading units against 768 for AMD, a 67% higher shader count, and 10 ray tracing cores against 12 for AMD. AMD still holds the edge in total RT cores, but Intel achieves its ray tracing capability with fewer cores and a lower power envelope. The Intel part also operates at a much lower base clock, 300 MHz versus 800 MHz, but boosts to 2400 MHz against 2700 MHz for AMD. The boost gap is narrower than the base gap, indicating that Intel relies more heavily on boost behavior to reach its performance class.

Both parts support the same API feature set: DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4. That means neither part has a feature-level advantage in API support. The differentiation is entirely in raw throughput, memory architecture, and integration approach.

Architecture Differences

The two GPUs come from different foundries and process nodes. AMD uses TSMC's 4 nm process with a Phoenix chip, while Intel uses its own 3 nm process with a Panther Lake chip. The AMD die measures 178 mm² and packs 25,390 million transistors, yielding a transistor density of 142.6 million per square millimeter. Intel does not disclose transistor count or die size for the Arc Pro B370, so density cannot be compared directly. The process node difference, 4 nm versus 3 nm, favors Intel in principle, but the missing die data prevents a quantitative density comparison.

Memory architecture diverges sharply. The AMD Ryzen Z1 Extreme GPU has 16 GB of dedicated LPDDR5 memory on a 64-bit bus, with 51.20 GB/s of bandwidth and an effective memory speed of 6.4 Gbps. The Intel Arc Pro B370 uses system shared memory, with the bus width, type, and bandwidth all marked as system dependent. That makes the Intel part an integrated GPU reliant on the host memory subsystem, while the AMD part carries its own dedicated memory pool. For workloads sensitive to memory bandwidth consistency, the AMD part has a fixed, known figure; the Intel part's bandwidth varies with the host platform.

Shader configuration differs as well. AMD uses 768 shading units, 48 texture mapping units, and 32 ROPs. Intel uses 1280 shading units, 40 TMUs, and 20 ROPs. The Intel part has more shaders but fewer TMUs and ROPs, which aligns with its lower texture and pixel rate figures. Ray tracing core counts are close: 12 for AMD, 10 for Intel. Neither part lists tensor cores, so AI acceleration is not quantified in the database.

Power and physical integration diverge significantly. The AMD part has a TDP of 30 W, while the Intel part draws 25 W. Both use no power connectors. The AMD part is a discrete card with dimensions of 280 mm by 111 mm by 21 mm, a single USB Type-C display output, and a 1x USB Type-C display configuration. The Intel part is an integrated GPU, marked as IGP for slot width and bus interface, with display outputs listed as portable device dependent. The Intel part has no recorded dimensions. The AMD part also has a launch MSRP of 699 USD, while the Intel part has no launch MSRP recorded.

Release timing also differs. The AMD Ryzen Z1 Extreme GPU entered production status as Active with a release date of June 12, 2023. The Intel Arc Pro B370 followed with a release date of January 26, 2026, and lists its predecessor as HD Graphics-WM. Both are currently marked Active in the database.

Where Each One Wins

The AMD Ryzen Z1 Extreme GPU wins on raw compute throughput. Its FP32 figure of 8.294 TFLOPS and FP16 figure of 16.59 TFLOPS exceed the Intel part's 6.144 TFLOPS and 12.29 TFLOPS respectively. That advantage applies to any workload that scales with floating-point operations, such as general-purpose compute, shader-heavy rendering, and physics simulations. The AMD part also wins on fill rate: 86.40 GPixel/s against 48.00 GPixel/s, and 129.6 GTexel/s against 96.00 GTexel/s. This makes the AMD part the stronger choice for resolution-heavy rasterization, where pixel and texture throughput directly influence frame output.

The AMD part also wins on memory determinism. With a fixed 16 GB LPDDR5 pool and a defined 51.20 GB/s bandwidth, it offers predictable memory behavior regardless of host platform. The Intel part's system shared memory introduces platform dependency, so its effective bandwidth cannot be stated as a fixed figure. For applications that require consistent memory performance, the AMD part has the recorded advantage.

The Intel Arc Pro B370 wins on integration and efficiency per watt in shader count. Its TDP of 25 W is lower than the AMD part's 30 W, and it achieves that with a higher shading unit count of 1280 versus 768. The Intel part also uses a more advanced process node, 3 nm versus 4 nm, which suggests better transistor-level efficiency, though Intel's transistor count and die size are not disclosed. The Intel part's IGP form factor means it requires no dedicated card slot, no power connector, and no discrete dimensions, making it suitable for compact portable devices where a discrete card cannot fit.

The Intel part also holds an advantage in shader count per TDP. With 1280 shading units at 25 W, it delivers 51.2 shading units per watt. The AMD part delivers 25.6 shading units per watt at 30 W. That is a 2x efficiency gap in shader throughput per watt, though the AMD part's higher clocks and larger ROP count change the overall performance picture.

The Verdict

The data points to two different design philosophies. The AMD Ryzen Z1 Extreme GPU is a discrete, self-contained graphics solution with dedicated memory and higher absolute throughput. Its 8.294 TFLOPS FP32, 86.40 GPixel/s pixel rate, and 129.6 GTexel/s texture rate make it the stronger part for raw rendering performance. The Intel Arc Pro B370 is an integrated GPU with a lower TDP, a more advanced process node, and a higher shader count, but it depends on system shared memory and delivers lower throughput figures across every measured rate: 6.144 TFLOPS FP32, 48.00 GPixel/s, and 96.00 GTexel/s.

For a workload that demands maximum compute and fill rate from a discrete part, the AMD Ryzen Z1 Extreme GPU is the choice. For an integrated, power-constrained design where the host platform supplies memory and the GPU must fit within an IGP slot, the Intel Arc Pro B370 is the applicable part. The database records no benchmark scores for either, so the verdict rests entirely on specification-level comparison.

The AMD part's 30 W TDP and 699 USD launch MSRP position it as a premium discrete mobile GPU. The Intel part's 25 W TDP, no recorded MSRP, and IGP designation position it as an embedded or portable integrated solution. Neither part shows a direct performance win in the recorded head-to-head set, because no head-to-head benchmarks exist. The specification record, however, favors AMD in compute, fill rate, and memory bandwidth, while favoring Intel in integration, process node, and shader count per watt.

FAQ

Q: Which GPU has higher FP32 compute performance?

A: The AMD Ryzen Z1 Extreme GPU delivers 8.294 TFLOPS of FP32, while the Intel Arc Pro B370 delivers 6.144 TFLOPS. AMD leads by roughly 35%.

Q: How do the memory configurations differ?

A: The AMD part uses 16 GB of dedicated LPDDR5 memory on a 64-bit bus with 51.20 GB/s bandwidth. The Intel part uses system shared memory, with bus width and bandwidth marked as system dependent.

Q: Which GPU has more shading units?

A: The Intel Arc Pro B370 has 1280 shading units, while the AMD Ryzen Z1 Extreme GPU has 768. Intel leads by 67% in shader count.

Q: What are the TDP ratings?

A: The AMD Ryzen Z1 Extreme GPU has a TDP of 30 W. The Intel Arc Pro B370 has a TDP of 25 W.

Q: Do both GPUs support the same APIs?

A: Yes. Both support DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4.

Q: Which GPU has the higher pixel rate?

A: The AMD Ryzen Z1 Extreme GPU has a pixel rate of 86.40 GPixel/s, while the Intel Arc Pro B370 has a pixel rate of 48.00 GPixel/s. AMD leads by 80%.

Q: What is the process node for each GPU?

A: The AMD Ryzen Z1 Extreme GPU uses TSMC's 4 nm process. The Intel Arc Pro B370 uses Intel's 3 nm process.